Accelerating Template-Based Matching on the GPU for AR Applications

Allusse, Yannick; Grasset, Raphaël; Billinghurst, Mark

doi:10.1109/ismar.2007.4538862

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the latter one, we want to study the use of mobile's Graphics Processor Units (GPU), since it is a common feature in nowadays mobiles. There are a few works at the moment [17], but they are not focused on mobile phones. The huge number of cores existing in current GPU provides these devices with computing capabilities that can be exploited by the marker tracking or the characteristic extraction that represent the second stage on CAR applications.…”

Section: Expected Contributionsmentioning

confidence: 99%

Improving the performance of CAR systems based on mobile phones

Bauset

Orduña

Morillo

2013

2013 International Conference on High Performance Computing &Amp; Simulation (HPCS)

View full text Add to dashboard Cite

Collaborative Augmented Reality (CAR) systems allow multiple users to share a real work environment including computer-generated images in real time. Currently, the hardware features of most mobile phones makes them a natural platform for CAR systems. However, the wide variety of these hardware features can have important effects on the performance of the mobile CAR applications. This thesis proposes a performance characterization and improvement of CAR systems based on mobile phones. The research results, at the time of writing this paper, shows that a CAR system using mobile phones as clients and with a single server can support up to one thousand clients while providing interactive response times.

show abstract

Section: Expected Contributionsmentioning

confidence: 99%

Improving the performance of CAR systems based on mobile phones

Bauset

Orduña

Morillo

2013

2013 International Conference on High Performance Computing &Amp; Simulation (HPCS)

View full text Add to dashboard Cite

show abstract

“…In [4], [1], and [11], template matching based on 2D correlation was implemented. Other works focused on key-point matching.…”

Section: Introductionmentioning

confidence: 99%

A GPU accelerated Fast Directional Chamfer Matching algorithm and a detailed comparison with a highly optimized CPU implementation

Rauter

Schreiber

2012

2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

In this work we present an efficient GPU implementation of the Fast Directional Chamfer Matching (FDCM) algorithm [10]. We propose some extensions to the original FDCM algorithm. In particular, we extend the algorithm to handle templates with variable size, to account for perspective effects. To the best of our knowledge, our work is the first to present a full implementation of a shape based matching algorithm on a GPU. Further contributions of our work consist of implementing a highly optimized CPU version of the algorithm (via multi-threading and SSE2), as well as a thorough comparison between pure GPU, pure CPU, and a hybrid version. The hybrid CPU-GPU version which turns out to be the fastest, achieves run-time of 44 fps on PAL resolution images.

show abstract

Accelerating Template-Based Matching on the GPU for AR Applications

Cited by 2 publications

References 6 publications

Improving the performance of CAR systems based on mobile phones

Improving the performance of CAR systems based on mobile phones

A GPU accelerated Fast Directional Chamfer Matching algorithm and a detailed comparison with a highly optimized CPU implementation

Contact Info

Product

Resources

About